# LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps

arXiv: https://arxiv.org/abs/2505.10593 · HTML: https://mlsanity.com/paper/2505.10593/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 41 references that are in the map.
- First posted on arXiv 15 May 2025.

## Builds on (most cited first, 11 of 11)

- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [AutoDroid: LLM-powered Task Automation in Android](https://mlsanity.com/paper/2308.15272/) (2023)
- [Software Testing with Large Language Models: Survey, Landscape, and Vision](https://mlsanity.com/paper/2307.07221/) (2023)
- [Enabling Conversational Interaction with Mobile UI using Large Language Models](https://mlsanity.com/paper/2209.08655/) (2022)
- [Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions](https://mlsanity.com/paper/2310.15780/) (2023)
- [Fill in the Blank: Context-aware Automated Text Input Generation for Mobile GUI Testing](https://mlsanity.com/paper/2212.04732/) (2022)
- [Autonomous Large Language Model Agents Enabling Intent-Driven Mobile GUI Testing](https://mlsanity.com/paper/2311.08649/) (2023)
- [Automatic Macro Mining from Interaction Traces at Scale](https://mlsanity.com/paper/2310.07023/) (2023)
- [Deep Reinforcement Learning for Black-Box Testing of Android Apps](https://mlsanity.com/paper/2101.02636/) (2021)
- [AUITestAgent: Automatic Requirements Oriented GUI Function Testing](https://mlsanity.com/paper/2407.09018/) (2024)
- [A Preliminary Study On the Sustainability of Android Malware Detection](https://mlsanity.com/paper/1807.08221/) (2018)

## Built on by (most cited first, 8 of 8)

- [PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint Tasks](https://mlsanity.com/paper/2606.31154/) (2026)
- [WebTestPilot: Agentic End-to-End Web Testing against Natural Language Specification by Inferring Oracles with Symbolized GUI Elements](https://mlsanity.com/paper/2602.11724/) (2026)
- [Do Multi-Agents Dream of Electric Screens? Achieving Perfect Accuracy on AndroidWorld Through Task Decomposition](https://mlsanity.com/paper/2602.07787/) (2026)
- [MANA: Towards Efficient Mobile Ad Detection via Multimodal Agentic UI Navigation](https://mlsanity.com/paper/2603.20351/) (2026)
- [MobileExplorer: Accelerating On-Device Inference for Mobile GUI Agents via Online Exploration](https://mlsanity.com/paper/2605.26546/) (2026)
- [Joint Agent Memory and Exploration Learning via Novelty Signals](https://mlsanity.com/paper/2606.01528/) (2026)
- [PastForward: Faster On-Device GUI Agents via Computational Experience Reuse](https://mlsanity.com/paper/2609.32166/) (2026)
- [Learning Reliable GUI Agents under Imperfect Priors](https://mlsanity.com/paper/2609.39547/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have opened new opportunities for automated mobile app exploration, an important and challenging problem that used to suffer from the difficulty of generating meaningful UI interactions. However, existing LLM-based exploration approaches rely heavily on LLMs to generate actions in almost every step, leading to a huge cost of token fees and computational resources. We argue that such extensive usage of LLMs is neither necessary nor effective, since many actions during exploration do not require, or may even be biased by the abilities of LLMs. Further, based on the insight that a precise and compact knowledge plays the central role for effective exploration, we introduce LLM-Explorer, a new exploration agent designed for efficiency and affordability. LLM-Explorer uses LLMs primarily for maintaining the knowledge instead of generating actions, and knowledge is used to guide action generation in a LLM-less manner. Based on a comparison with 5 strong baselines on 20 typical apps, LLM-Explorer was able to achieve the fastest and highest coverage among all automated app explorers, with over 148x lower cost than the state-of-the-art LLM-based approach.